Frozen-DETR: Enhancing DETR with Image Understanding from Frozen Foundation Models

Recent vision foundation models can extract universal representations and show impressive abilities in various tasks. However, their application on object detection is largely overlooked, especially without fine-tuning them. In this work, we show that frozen foundation models can be a versatile feature enhancer, even though they are not pre-trained for object detection. Specifically, we explore directly transferring the high-level image understanding of foundation models to detectors in the following two ways. First, the class token in foundation models provides an in-depth understanding of the complex scene, which facilitates decoding object queries in the detector's decoder by providing a compact context. Additionally, the patch tokens in foundation models can enrich the features in the detector's encoder by providing semantic details. Utilizing frozen foundation models as plug-and-play modules rather than the commonly used backbone can significantly enhance the detector's performance while preventing the problems caused by the architecture discrepancy between the detector's backbone and the foundation model. With such a novel paradigm, we boost the SOTA query-based detector DINO from 49.0% AP to 51.9% AP (+2.9% AP) and further to 53.8% AP (+4.8% AP) by integrating one or two foundation models respectively, on the COCO validation set after training for 12 epochs with R50 as the detector's backbone.

Real-to-Sim Grasp: Rethinking the Gap between Simulation and Real World in Grasp Detection

For 6-DoF grasp detection, simulated data is expandable to train more powerful model, but it faces the challenge of the large gap between simulation and real world. Previous works bridge this gap with a sim-to-real way. However, this way explicitly or implicitly forces the simulated data to adapt to the noisy real data when training grasp detectors, where the positional drift and structural distortion within the camera noise will harm the grasp learning. In this work, we propose a Real-to-Sim framework for 6-DoF Grasp detection, named R2SGrasp, with the key insight of bridging this gap in a real-to-sim way, which directly bypasses the camera noise in grasp detector training through an inference-time real-to-sim adaption. To achieve this real-to-sim adaptation, our R2SGrasp designs the Real-to-Sim Data Repairer (R2SRepairer) to mitigate the camera noise of real depth maps in data-level, and the Real-to-Sim Feature Enhancer (R2SEnhancer) to enhance real features with precise simulated geometric primitives in feature-level. To endow our framework with the generalization ability, we construct a large-scale simulated dataset cost-efficiently to train our grasp detector, which includes 64,000 RGB-D images with 14.4 million grasp annotations. Sufficient experiments show that R2SGrasp is powerful and our real-to-sim perspective is effective. The real-world experiments further show great generalization ability of R2SGrasp. Project page is available on https://isee-laboratory.github.io/R2SGrasp.

Towards Completeness: A Generalizable Action Proposal Generator for Zero-Shot Temporal Action Localization

To address the zero-shot temporal action localization (ZSTAL) task, existing works develop models that are generalizable to detect and classify actions from unseen categories. They typically develop a category-agnostic action detector and combine it with the Contrastive Language-Image Pre-training (CLIP) model to solve ZSTAL. However, these methods suffer from incomplete action proposals generated for \textit{unseen} categories, since they follow a frame-level prediction paradigm and require hand-crafted post-processing to generate action proposals. To address this problem, in this work, we propose a novel model named Generalizable Action Proposal generator (GAP), which can interface seamlessly with CLIP and generate action proposals in a holistic way. Our GAP is built in a query-based architecture and trained with a proposal-level objective, enabling it to estimate proposal completeness and eliminate the hand-crafted post-processing. Based on this architecture, we propose an Action-aware Discrimination loss to enhance the category-agnostic dynamic information of actions. Besides, we introduce a Static-Dynamic Rectifying module that incorporates the generalizable static information from CLIP to refine the predicted proposals, which improves proposal completeness in a generalizable manner. Our experiments show that our GAP achieves state-of-the-art performance on two challenging ZSTAL benchmarks, i.e., Thumos14 and ActivityNet1.3. Specifically, our model obtains significant performance improvement over previous works on the two benchmarks, i.e., +3.2% and +3.4% average mAP, respectively.

ParGo: Bridging Vision-Language with Partial and Global Views

This work presents ParGo, a novel Partial-Global projector designed to connect the vision and language modalities for Multimodal Large Language Models (MLLMs). Unlike previous works that rely on global attention-based projectors, our ParGo bridges the representation gap between the separately pre-trained vision encoders and the LLMs by integrating global and partial views, which alleviates the overemphasis on prominent regions. To facilitate the effective training of ParGo, we collect a large-scale detail-captioned image-text dataset named ParGoCap-1M-PT, consisting of 1 million images paired with high-quality captions. Extensive experiments on several MLLM benchmarks demonstrate the effectiveness of our ParGo, highlighting its superiority in aligning vision and language modalities. Compared to conventional Q-Former projector, our ParGo achieves an improvement of 259.96 in MME benchmark. Furthermore, our experiments reveal that ParGo significantly outperforms other projectors, particularly in tasks that emphasize detail perception ability.

PixelFade: Privacy-preserving Person Re-identification with Noise-guided Progressive Replacement

Online person re-identification services face privacy breaches from potential data leakage and recovery attacks, exposing cloud-stored images to malicious attackers and triggering public concern. The privacy protection of pedestrian images is crucial. Previous privacy-preserving person re-identification methods are unable to resist recovery attacks and compromise accuracy. In this paper, we propose an iterative method (PixelFade) to optimize pedestrian images into noise-like images to resist recovery attacks. We first give an in-depth study of protected images from previous privacy methods, which reveal that the chaos of protected images can disrupt the learning of recovery models. Accordingly, Specifically, we propose Noise-guided Objective Function with the feature constraints of a specific authorization model, optimizing pedestrian images to normal-distributed noise images while preserving their original identity information as per the authorization model. To solve the above non-convex optimization problem, we propose a heuristic optimization algorithm that alternately performs the Constraint Operation and the Partial Replacement Operation. This strategy not only safeguards that original pixels are replaced with noises to protect privacy, but also guides the images towards an improved optimization direction to effectively preserve discriminative features. Extensive experiments demonstrate that our PixelFade outperforms previous methods in resisting recovery attacks and Re-ID performance. The code is available at https://github.com/iSEE-Laboratory/PixelFade.

Loc4Plan: Locating Before Planning for Outdoor Vision and Language Navigation

Vision and Language Navigation (VLN) is a challenging task that requires agents to understand instructions and navigate to the destination in a visual environment.One of the key challenges in outdoor VLN is keeping track of which part of the instruction was completed. To alleviate this problem, previous works mainly focus on grounding the natural language to the visual input, but neglecting the crucial role of the agent's spatial position information in the grounding process. In this work, we first explore the substantial effect of spatial position locating on the grounding of outdoor VLN, drawing inspiration from human navigation. In real-world navigation scenarios, before planning a path to the destination, humans typically need to figure out their current location. This observation underscores the pivotal role of spatial localization in the navigation process. In this work, we introduce a novel framework, Locating be for Planning (Loc4Plan), designed to incorporate spatial perception for action planning in outdoor VLN tasks. The main idea behind Loc4Plan is to perform the spatial localization before planning a decision action based on corresponding guidance, which comprises a block-aware spatial locating (BAL) module and a spatial-aware action planning (SAP) module. Specifically, to help the agent perceive its spatial location in the environment, we propose to learn a position predictor that measures how far the agent is from the next intersection for reflecting its position, which is achieved by the BAL module. After the locating process, we propose the SAP module to incorporate spatial information to ground the corresponding guidance and enhance the precision of action planning. Extensive experiments on the Touchdown and map2seq datasets show that the proposed Loc4Plan outperforms the SOTA methods.

SynopGround: A Large-Scale Dataset for Multi-Paragraph Video Grounding from TV Dramas and Synopses

Video grounding is a fundamental problem in multimodal content understanding, aiming to localize specific natural language queries in an untrimmed video. However, current video grounding datasets merely focus on simple events and are either limited to shorter videos or brief sentences, which hinders the model from evolving toward stronger multimodal understanding capabilities. To address these limitations, we present a large-scale video grounding dataset named SynopGround, in which more than 2800 hours of videos are sourced from popular TV dramas and are paired with accurately localized human-written synopses. Each paragraph in the synopsis serves as a language query and is manually annotated with precise temporal boundaries in the long video. These paragraph queries are tightly correlated to each other and contain a wealth of abstract expressions summarizing video storylines and specific descriptions portraying event details, which enables the model to learn multimodal perception on more intricate concepts over longer context dependencies. Based on the dataset, we further introduce a more complex setting of video grounding dubbed Multi-Paragraph Video Grounding (MPVG), which takes as input multiple paragraphs and a long video for grounding each paragraph query to its temporal interval. In addition, we propose a novel Local-Global Multimodal Reasoner (LGMR) to explicitly model the local-global structures of long-term multimodal inputs for MPVG. Our method provides an effective baseline solution to the multi-paragraph video grounding problem. Extensive experiments verify the proposed model's effectiveness as well as its superiority in long-term multi-paragraph video grounding over prior state-of-the-arts. Dataset and code are publicly available. Project page: https://synopground.github.io/.

PRET: Planning with Directed Fidelity Trajectory for Vision and Language Navigation

Vision and language navigation is a task that requires an agent to navigate according to a natural language instruction. Recent methods predict sub-goals on constructed topology map at each step to enable long-term action planning. However, they suffer from high computational cost when attempting to support such high-level predictions with GCN-like models. In this work, we propose an alternative method that facilitates navigation planning by considering the alignment between instructions and directed fidelity trajectories, which refers to a path from the initial node to the candidate locations on a directed graph without detours. This planning strategy leads to an efficient model while achieving strong performance. Specifically, we introduce a directed graph to illustrate the explored area of the environment, emphasizing directionality. Then, we firstly define the trajectory representation as a sequence of directed edge features, which are extracted from the panorama based on the corresponding orientation. Ultimately, we assess and compare the alignment between instruction and different trajectories during navigation to determine the next navigation target. Our method outperforms previous SOTA method BEVBert on RxR dataset and is comparable on R2R dataset while largely reducing the computational cost. Code is available: https://github.com/iSEE-Laboratory/VLN-PRET.

Bridge Past and Future: Overcoming Information Asymmetry in Incremental Object Detection

In incremental object detection, knowledge distillation has been proven to be an effective way to alleviate catastrophic forgetting. However, previous works focused on preserving the knowledge of old models, ignoring that images could simultaneously contain categories from past, present, and future stages. The co-occurrence of objects makes the optimization objectives inconsistent across different stages since the definition for foreground objects differs across various stages, which limits the model's performance greatly. To overcome this problem, we propose a method called ``Bridge Past and Future'' (BPF), which aligns models across stages, ensuring consistent optimization directions. In addition, we propose a novel Distillation with Future (DwF) loss, fully leveraging the background probability to mitigate the forgetting of old classes while ensuring a high level of adaptability in learning new classes. Extensive experiments are conducted on both Pascal VOC and MS COCO benchmarks. Without memory, BPF outperforms current state-of-the-art methods under various settings. The code is available at https://github.com/iSEE-Laboratory/BPF.

Human-Centric Transformer for Domain Adaptive Action Recognition

We study the domain adaptation task for action recognition, namely domain adaptive action recognition, which aims to effectively transfer action recognition power from a label-sufficient source domain to a label-free target domain. Since actions are performed by humans, it is crucial to exploit human cues in videos when recognizing actions across domains. However, existing methods are prone to losing human cues but prefer to exploit the correlation between non-human contexts and associated actions for recognition, and the contexts of interest agnostic to actions would reduce recognition performance in the target domain. To overcome this problem, we focus on uncovering human-centric action cues for domain adaptive action recognition, and our conception is to investigate two aspects of human-centric action cues, namely human cues and human-context interaction cues. Accordingly, our proposed Human-Centric Transformer (HCTransformer) develops a decoupled human-centric learning paradigm to explicitly concentrate on human-centric action cues in domain-variant video feature learning. Our HCTransformer first conducts human-aware temporal modeling by a human encoder, aiming to avoid a loss of human cues during domain-invariant video feature learning. Then, by a Transformer-like architecture, HCTransformer exploits domain-invariant and action-correlated contexts by a context encoder, and further models domain-invariant interaction between humans and action-correlated contexts. We conduct extensive experiments on three benchmarks, namely UCF-HMDB, Kinetics-NecDrone and EPIC-Kitchens-UDA, and the state-of-the-art performance demonstrates the effectiveness of our proposed HCTransformer.