Contrastive Language-Image Pretraining (CLIP) models maximize the mutual information between text and visual modalities to learn representations. This makes the nature of the training data a significant factor in the efficacy of CLIP for downstream tasks. However, the lack of compositional diversity in contemporary image-text datasets limits the compositional reasoning ability of CLIP. We show that generating ``hard'' negative captions via in-context learning and synthesizing corresponding negative images with text-to-image generators offers a solution. We introduce a novel contrastive pre-training strategy that leverages these hard negative captions and images in an alternating fashion to train CLIP. We demonstrate that our method, named TripletCLIP, when applied to existing datasets such as CC3M and CC12M, enhances the compositional capabilities of CLIP, resulting in an absolute improvement of over 9% on the SugarCrepe benchmark on an equal computational budget, as well as improvements in zero-shot image classification and image retrieval. Our code, models, and data are available at: https://tripletclip.github.io

Downsampling operators break the shift invariance of convolutional neural networks (CNNs) and this affects the robustness of features learned by CNNs when dealing with even small pixel-level shift. Through a large-scale correlation analysis framework, we study shift invariance of CNNs by inspecting existing downsampling operators in terms of their maximum-sampling bias (MSB), and find that MSB is negatively correlated with shift invariance. Based on this crucial insight, we propose a learnable pooling operator called Translation Invariant Polyphase Sampling (TIPS) and two regularizations on the intermediate feature maps of TIPS to reduce MSB and learn translation-invariant representations. TIPS can be integrated into any CNN and can be trained end-to-end with marginal computational overhead. Our experiments demonstrate that TIPS results in consistent performance gains in terms of accuracy, shift consistency, and shift fidelity on multiple benchmarks for image classification and semantic segmentation compared to previous methods and also leads to improvements in adversarial and distributional robustness. TIPS results in the lowest MSB compared to all previous methods, thus explaining our strong empirical results.

Spatial understanding is a fundamental aspect of computer vision and integral for human-level reasoning about images, making it an important component for grounded language understanding. While recent text-to-image synthesis (T2I) models have shown unprecedented improvements in photorealism, it is unclear whether they have reliable spatial understanding capabilities. We investigate the ability of T2I models to generate correct spatial relationships among objects and present VISOR, an evaluation metric that captures how accurately the spatial relationship described in text is generated in the image. To benchmark existing models, we introduce a dataset, $\mathrm{SR}_{2D}$, that contains sentences describing two or more objects and the spatial relationships between them. We construct an automated evaluation pipeline to recognize objects and their spatial relationships, and employ it in a large-scale evaluation of T2I models. Our experiments reveal a surprising finding that, although state-of-the-art T2I models exhibit high image quality, they are severely limited in their ability to generate multiple objects or the specified spatial relations between them. Our analyses demonstrate several biases and artifacts of T2I models such as the difficulty with generating multiple objects, a bias towards generating the first object mentioned, spatially inconsistent outputs for equivalent relationships, and a correlation between object co-occurrence and spatial understanding capabilities. We conduct a human study that shows the alignment between VISOR and human judgement about spatial understanding. We offer the $\mathrm{SR}_{2D}$ dataset and the VISOR metric to the community in support of T2I reasoning research.

The ability to understand visual concepts and replicate and compose these concepts from images is a central goal for computer vision. Recent advances in text-to-image (T2I) models have lead to high definition and realistic image quality generation by learning from large databases of images and their descriptions. However, the evaluation of T2I models has focused on photorealism and limited qualitative measures of visual understanding. To quantify the ability of T2I models in learning and synthesizing novel visual concepts, we introduce ConceptBed, a large-scale dataset that consists of 284 unique visual concepts, 5K unique concept compositions, and 33K composite text prompts. Along with the dataset, we propose an evaluation metric, Concept Confidence Deviation (CCD), that uses the confidence of oracle concept classifiers to measure the alignment between concepts generated by T2I generators and concepts contained in ground truth images. We evaluate visual concepts that are either objects, attributes, or styles, and also evaluate four dimensions of compositionality: counting, attributes, relations, and actions. Our human study shows that CCD is highly correlated with human understanding of concepts. Our results point to a trade-off between learning the concepts and preserving the compositionality which existing approaches struggle to overcome.

We investigate knowledge retrieval with multi-modal queries, i.e. queries containing information split across image and text inputs, a challenging task that differs from previous work on cross-modal retrieval. We curate a new dataset called ReMuQ for benchmarking progress on this task. ReMuQ requires a system to retrieve knowledge from a large corpus by integrating contents from both text and image queries. We introduce a retriever model ``ReViz'' that can directly process input text and images to retrieve relevant knowledge in an end-to-end fashion without being dependent on intermediate modules such as object detectors or caption generators. We introduce a new pretraining task that is effective for learning knowledge retrieval with multimodal queries and also improves performance on downstream tasks. We demonstrate superior performance in retrieval on two datasets (ReMuQ and OK-VQA) under zero-shot settings as well as further improvements when finetuned on these datasets.

In this work, we present a data poisoning attack that confounds machine learning models without any manipulation of the image or label. This is achieved by simply leveraging the most confounding natural samples found within the training data itself, in a new form of a targeted attack coined "Mole Recruitment." We define moles as the training samples of a class that appear most similar to samples of another class, and show that simply restructuring training batches with an optimal number of moles can lead to significant degradation in the performance of the targeted class. We show the efficacy of this novel attack in an offline setting across several standard image classification datasets, and demonstrate the real-world viability of this attack in a continual learning (CL) setting. Our analysis reveals that state-of-the-art models are susceptible to Mole Recruitment, thereby exposing a previously undetected vulnerability of image classifiers.

Captioning is a crucial and challenging task for video understanding. In videos that involve active agents such as humans, the agent's actions can bring about myriad changes in the scene. Observable changes such as movements, manipulations, and transformations of the objects in the scene, are reflected in conventional video captioning. Unlike images, actions in videos are also inherently linked to social aspects such as intentions (why the action is taking place), effects (what changes due to the action), and attributes that describe the agent. Thus for video understanding, such as when captioning videos or when answering questions about videos, one must have an understanding of these commonsense aspects. We present the first work on generating commonsense captions directly from videos, to describe latent aspects such as intentions, effects, and attributes. We present a new dataset "Video-to-Commonsense (V2C)" that contains $\sim9k$ videos of human agents performing various actions, annotated with 3 types of commonsense descriptions. Additionally we explore the use of open-ended video-based commonsense question answering (V2C-QA) as a way to enrich our captions. Both the generation task and the QA task can be used to enrich video captions.

To be successful in single source domain generalization, maximizing diversity of synthesized domains has emerged as one of the most effective strategies. Many of the recent successes have come from methods that pre-specify the types of diversity that a model is exposed to during training, so that it can ultimately generalize well to new domains. However, na\"ive diversity based augmentations do not work effectively for domain generalization either because they cannot model large domain shift, or because the span of transforms that are pre-specified do not cover the types of shift commonly occurring in domain generalization. To address this issue, we present a novel framework that uses adversarially learned transformations (ALT) using a neural network to model plausible, yet hard image transformations that fool the classifier. This network is randomly initialized for each batch and trained for a fixed number of steps to maximize classification error. Further, we enforce consistency between the classifier's predictions on the clean and transformed images. With extensive empirical analysis, we find that this new form of adversarial transformations achieve both objectives of diversity and hardness simultaneously, outperforming all existing techniques on competitive benchmarks for single source domain generalization. We also show that ALT can naturally work with existing diversity modules to produce highly distinct, and large transformations of the source domain leading to state-of-the-art performance.

The process of identifying changes or transformations in a scene along with the ability of reasoning about their causes and effects, is a key aspect of intelligence. In this work we go beyond recent advances in computational perception, and introduce a more challenging task, Image-based Event-Sequencing (IES). In IES, the task is to predict a sequence of actions required to rearrange objects from the configuration in an input source image to the one in the target image. IES also requires systems to possess inductive generalizability. Motivated from evidence in cognitive development, we compile the first IES dataset, the Blocksworld Image Reasoning Dataset (BIRD) which contains images of wooden blocks in different configurations, and the sequence of moves to rearrange one configuration to the other. We first explore the use of existing deep learning architectures and show that these end-to-end methods under-perform in inferring temporal event-sequences and fail at inductive generalization. We then propose a modular two-step approach: Visual Perception followed by Event-Sequencing, and demonstrate improved performance by combining learning and reasoning. Finally, by showing an extension of our approach on natural images, we seek to pave the way for future research on event sequencing for real world scenes.