DCDepth: Progressive Monocular Depth Estimation in Discrete Cosine Domain
In this paper, we introduce DCDepth, a novel framework for the long-standing monocular depth estimation task. Moving beyond conventional pixel-wise depth estimation in the spatial domain, our approach estimates the frequency coefficients of depth patches after transforming them into the discrete cosine domain. This unique formulation allows for the modeling of local depth correlations within each patch.
76b878f34e43c5faeba770c840bec394-Paper-Conference.pdf
Collaborative trajectory prediction can comprehensively forecast the future motion of objects through multi-view complementary information. However, it encounters two main challenges in multi-drone collaboration settings. The expansive aerial observations make it difficult to generate precise Bird's Eye View (BEV) representations. Besides, excessive interactions can not meet real-time prediction requirements within the constrained drone-based communication bandwidth. To address these problems, we propose a novel framework named "Drones Help Drones" (DHD).
SearchLVLMs: A Plug-and-Play Framework for Augmenting Large Vision-Language Models by Searching Up-to-Date Internet Knowledge
Large vision-language models (LVLMs) are ignorant of the up-to-date knowledge, such as LLaVA series, because they cannot be updated frequently due to the large amount of resources required, and therefore fail in many cases. For example, if a LVLM was released on January 2024, and it wouldn't know the singer of the theme song for the new Detective Conan movie, which wasn't released until April 2024. To solve the problem, a promising solution motivated by retrievalaugmented generation (RAG) is to provide LVLMs with up-to-date knowledge via internet search during inference, i.e., internet-augmented generation (IAG), which is already integrated in some closed-source commercial LVLMs such as GPT-4V. However, the specific mechanics underpinning them remain a mystery. In this paper, we propose a plug-and-play framework, for augmenting existing LVLMs in handling visual question answering (VQA) about up-to-date knowledge, dubbed SearchLVLMs. A hierarchical filtering model is trained to effectively and efficiently find the most helpful content from the websites returned by a search engine to prompt LVLMs with up-to-date knowledge. To train the model and evaluate our framework's performance, we propose a pipeline to automatically generate newsrelated VQA samples to construct a dataset, dubbed UDK-VQA. A multi-model voting mechanism is introduced to label the usefulness of website/content for VQA samples to construct the training set. Experimental results demonstrate the effectiveness of our framework, outperforming GPT-4o by 30% in accuracy.
Appendix: Learning Black-Box Attackers with Transferable Priors and Query Feedback
We illustrate the complete SimBA+, SimBA++, Learnable Black-Box Attack (LeBA) and High-Order Gradient Approximation (HOGA) in Algorithm A1, Algorithm A2 and Algorithm A3, respectively. Surrogate models for black-box attack in vision models are generally available, since the visual saliency from various vision models is expected to be consistent. In Figure A1, we illustrate the gradients from Inception-V3 [15] and ResNet-152 [9]. Randomly selected images before and after adversarial attack by LeBA are illustrated in Figure A2. These authors have contributed equally.
Reinforcement Learning with Lookahead Information
We study reinforcement learning (RL) problems in which agents observe the reward or transition realizations at their current state before deciding which action to take. Such observations are available in many applications, including transactions, navigation and more. When the environment is known, previous work shows that this lookahead information can drastically increase the collected reward. However, outside of specific applications, existing approaches for interacting with unknown environments are not well-adapted to these observations. In this work, we close this gap and design provably-efficient learning algorithms able to incorporate lookahead information. To achieve this, we perform planning using the empirical distribution of the reward and transition observations, in contrast to vanilla approaches that only rely on estimated expectations. We prove that our algorithms achieve tight regret versus a baseline that also has access to lookahead information - linearly increasing the amount of collected reward compared to agents that cannot handle lookahead information.
Stochastic contextual bandits with graph feedback: from independence number to MAS number Yuxiao Wen Yanjun Han Zhengyuan Zhou,* New York University
We consider contextual bandits with graph feedback, a class of interactive learning problems with richer structures than vanilla contextual bandits, where taking an action reveals the rewards for all neighboring actions in the feedback graph under all contexts. Unlike the multi-armed bandits setting where a growing literature has painted a near-complete understanding of graph feedback, much remains unexplored in the contextual bandits counterpart.
HEALNet: Multimodal Fusion for Heterogeneous Biomedical Data
Technological advances in medical data collection, such as high-throughput genomic sequencing and digital high-resolution histopathology, have contributed to the rising requirement for multimodal biomedical modelling, specifically for image, tabular and graph data. Most multimodal deep learning approaches use modality-specific architectures that are often trained separately and cannot capture the crucial cross-modal information that motivates the integration of different data sources. This paper presents the Hybrid Early-fusion Attention Learning Network (HEALNet) - a flexible multimodal fusion architecture, which: a) preserves modality-specific structural information, b) captures the cross-modal interactions and structural information in a shared latent space, c) can effectively handle missing modalities during training and inference, and d) enables intuitive model inspection by learning on the raw data input instead of opaque embeddings. We conduct multimodal survival analysis on Whole Slide Images and Multi-omic data on four cancer datasets from The Cancer Genome Atlas (TCGA). HEALNet achieves state-of-the-art performance compared to other end-to-end trained fusion models, substantially improving over unimodal and multimodal baselines whilst being robust in scenarios with missing modalities.
Learning Distinguishable Trajectory Representation with Contrastive Loss Tianxu Li1,2 Juan Li1 Yang Zhang
Policy network parameter sharing is a commonly used technique in advanced deep multi-agent reinforcement learning (MARL) algorithms to improve learning efficiency by reducing the number of policy parameters and sharing experiences among agents. Nevertheless, agents that share the policy parameters tend to learn similar behaviors. To encourage multi-agent diversity, prior works typically maximize the mutual information between trajectories and agent identities using variational inference. However, this category of methods easily leads to inefficient exploration due to limited trajectory visitations. To resolve this limitation, inspired by the learning of pre-trained models, in this paper, we propose a novel Contrastive Trajectory Representation (CTR) method based on learning distinguishable trajectory representations to encourage multi-agent diversity.
1 Hosting, Licensing, and Maintenance Plan
Our dataset, MIA, will be hosted by AirLab at Carnegie Mellon University (CMU). The dataset will be available for a minimum of five years, with no plans for removal. We will ensure ongoing maintenance to verify and maintain data accessibility. The first-personview images and associated metadata of the MIA dataset are published under the CC-By-SA license, similar to Mapillary. The bird's eye view map of MIA dataset is published under ODbL following OpenStreetMap. We, the authors, bear all responsibility in case of violation of rights, etc., and confirmation of data license. For what purpose was the dataset created?