We propose a training-free method for open-vocabulary semantic segmentation using Vision-and-Language Models (VLMs). Our approach enhances the initial per-patch predictions of VLMs through label propagation, which jointly optimizes predictions by incorporating patch-to-patch relationships. Since VLMs are primarily optimized for cross-modal alignment and not for intra-modal similarity, we use a Vision Model (VM) that is observed to better capture these relationships. We address resolution limitations inherent to patch-based encoders by applying label propagation at the pixel level as a refinement step, significantly improving segmentation accuracy near class boundaries. Our method, called LPOSS+, performs inference over the entire image, avoiding window-based processing and thereby capturing contextual interactions across the full image. LPOSS+ achieves state-of-the-art performance among training-free methods, across a diverse set of datasets. Code: https://github.com/vladan-stojnic/LPOSS

Recent multi-teacher distillation methods have unified the encoders of multiple foundation models into a single encoder, achieving competitive performance on core vision tasks like classification, segmentation, and depth estimation. This led us to ask: Could similar success be achieved when the pool of teachers also includes vision models specialized in diverse tasks across both 2D and 3D perception? In this paper, we define and investigate the problem of heterogeneous teacher distillation, or co-distillation, a challenging multi-teacher distillation scenario where teacher models vary significantly in both (a) their design objectives and (b) the data they were trained on. We explore data-sharing strategies and teacher-specific encoding, and introduce DUNE, a single encoder excelling in 2D vision, 3D understanding, and 3D human perception. Our model achieves performance comparable to that of its larger teachers, sometimes even outperforming them, on their respective tasks. Notably, DUNE surpasses MASt3R in Map-free Visual Relocalization with a much smaller encoder.

Vision-Language Models (VLMs) have demonstrated impressive performance on zero-shot classification, i.e. classification when provided merely with a list of class names. In this paper, we tackle the case of zero-shot classification in the presence of unlabeled data. We leverage the graph structure of the unlabeled data and introduce ZLaP, a method based on label propagation (LP) that utilizes geodesic distances for classification. We tailor LP to graphs containing both text and image features and further propose an efficient method for performing inductive inference based on a dual solution and a sparsification step. We perform extensive experiments to evaluate the effectiveness of our method on 14 common datasets and show that ZLaP outperforms the latest related works. Code: https://github.com/vladan-stojnic/ZLaP

Recent image generation models such as Stable Diffusion have exhibited an impressive ability to generate fairly realistic images starting from a simple text prompt. Could such models render real images obsolete for training image prediction models? In this paper, we answer part of this provocative question by investigating the need for real images when training models for ImageNet classification. Provided only with the class names that have been used to build the dataset, we explore the ability of Stable Diffusion to generate synthetic clones of ImageNet and measure how useful these are for training classification models from scratch. We show that with minimal and class-agnostic prompt engineering, ImageNet clones are able to close a large part of the gap between models produced by synthetic images and models trained with real images, for the several standard classification benchmarks that we consider in this study. More importantly, we show that models trained on synthetic images exhibit strong generalization properties and perform on par with models trained on real data for transfer. Project page: https://europe.naverlabs.com/imagenet-sd/

We consider the problem of training a deep neural network on a given classification task, e.g., ImageNet-1K (IN1K), so that it excels at both the training task as well as at other (future) transfer tasks. These two seemingly contradictory properties impose a trade-off between improving the model's generalization and maintaining its performance on the original task. Models trained with self-supervised learning tend to generalize better than their supervised counterparts for transfer learning; yet, they still lag behind supervised models on IN1K. In this paper, we propose a supervised learning setup that leverages the best of both worlds. We extensively analyze supervised training using multi-scale crops for data augmentation and an expendable projector head, and reveal that the design of the projector allows us to control the trade-off between performance on the training task and transferability. We further replace the last layer of class weights with class prototypes computed on the fly using a memory bank and derive two models: t-ReX that achieves a new state of the art for transfer learning and outperforms top methods such as DINO and PAWS on IN1K, and t-ReX* that matches the highly optimized RSB-A1 model on IN1K while performing better on transfer tasks. Code and pretrained models: https://europe.naverlabs.com/t-rex

Dimensionality reduction methods are unsupervised approaches which learn low-dimensional spaces where some properties of the initial space, typically the notion of "neighborhood", are preserved. They are a crucial component of diverse tasks like visualization, compression, indexing, and retrieval. Aiming for a totally different goal, self-supervised visual representation learning has been shown to produce transferable representation functions by learning models that encode invariance to artificially created distortions, e.g. a set of hand-crafted image transformations. Unlike manifold learning methods that usually require propagation on large k-NN graphs or complicated optimization solvers, self-supervised learning approaches rely on simpler and more scalable frameworks for learning. In this paper, we unify these two families of approaches from the angle of manifold learning and propose TLDR, a dimensionality reduction method for generic input spaces that is porting the simple self-supervised learning framework of Barlow Twins to a setting where it is hard or impossible to define an appropriate set of distortions by hand. We propose to use nearest neighbors to build pairs from a training set and a redundancy reduction loss borrowed from the self-supervised literature to learn an encoder that produces representations invariant across such pairs. TLDR is a method that is simple, easy to implement and train, and of broad applicability; it consists of an offline nearest neighbor computation step that can be highly approximated, and a straightforward learning process that does not require mining negative samples to contrast, eigendecompositions, or cumbersome optimization solvers. By replacing PCA with TLDR, we are able to increase the performance of GeM-AP by 4% mAP for 128 dimensions, and to retain its performance with 16x fewer dimensions.

This is the proceedings of the Computer Vision for Agriculture (CV4A) Workshop that was held in conjunction with the International Conference on Learning Representations (ICLR) 2020. The Computer Vision for Agriculture (CV4A) 2020 workshop was scheduled to be held in Addis Ababa, Ethiopia, on April 26th, 2020. It was held virtually that same day due to the COVID-19 pandemic. The workshop was held in conjunction with the International Conference on Learning Representations (ICLR) 2020.

Learning to capture long-range relations is fundamental to image/video recognition. Existing CNN models generally rely on increasing depth to model such relations which is highly inefficient. In this work, we propose the “double attention block”, a novel component that aggregates and propagates informative global features from the entire spatio-temporal space of input images/videos, enabling subsequent convolution layers to access features from the entire space efficiently. The component is designed with a double attention mechanism in two steps, where the first step gathers features from the entire space into a compact set through second-order attention pooling and the second step adaptively selects and distributes features to each location via another attention. The proposed double attention block is easy to adopt and can be plugged into existing deep neural networks conveniently. We conduct extensive ablation studies and experiments on both image and video recognition tasks for evaluating its performance. On the image recognition task, a ResNet-50 equipped with our double attention blocks outperforms a much larger ResNet-152 architecture on ImageNet-1k dataset with over 40% less the number of parameters and less FLOPs. On the action recognition task, our proposed model achieves the state-of-the-art results on the Kinetics and UCF-101 datasets with significantly higher efficiency than recent works.

Learning to capture long-range relations is fundamental to image/video recognition. Existing CNN models generally rely on increasing depth to model such relations which is highly inefficient. In this work, we propose the "double attention block", a novel component that aggregates and propagates informative global features from the entire spatio-temporal space of input images/videos, enabling subsequent convolution layers to access features from the entire space efficiently. The component is designed with a double attention mechanism in two steps, where the first step gathers features from the entire space into a compact set through second-order attention pooling and the second step adaptively selects and distributes features to each location via another attention. The proposed double attention block is easy to adopt and can be plugged into existing deep neural networks conveniently. We conduct extensive ablation studies and experiments on both image and video recognition tasks for evaluating its performance. On the image recognition task, a ResNet-50 equipped with our double attention blocks outperforms a much larger ResNet-152 architecture on ImageNet-1k dataset with over 40% less the number of parameters and less FLOPs. On the action recognition task, our proposed model achieves the state-of-the-art results on the Kinetics and UCF-101 datasets with significantly higher efficiency than recent works.

The boom of mobile devices and cloud services has led to an explosion of personal photo and video data. However, due to the missing user-generated metadata such as titles or descriptions, it usually takes a user a lot of swipes to find some video on the cell phone. To solve the problem, we present an innovative idea called Visual Memory QA which allow a user not only to search but also to ask questions about her daily life captured in the personal videos. The proposed system automatically analyzes the content of personal videos without user-generated metadata, and offers a conversational interface to accept and answer questions. To the best of our knowledge, it is the first to answer personal questions discovered in personal photos or videos. The example questions are "what was the lat time we went hiking in the forest near San Francisco?"; "did we have pizza last week?"; "with whom did I have dinner in AAAI 2015?".