Related papers: CATP: Confidence-Aware Token Pruning for Camouflag…

Accurately detecting and tracking multi-objects is important for safety-critical applications such as autonomous navigation. However, it remains challenging to provide guarantees on the performance of state-of-the-art techniques based on…

Transformer-based models have achieved dominant performance in numerous NLP tasks. Despite their remarkable successes, pre-trained transformers such as BERT suffer from a computationally expensive self-attention mechanism that interacts…

Camouflaged objects are seamlessly blended in with their surroundings, which brings a challenging detection task in computer vision. Optimizing a convolutional neural network (CNN) for camouflaged object detection (COD) tends to activate…

Vision tokens in multimodal large language models often dominate huge computational overhead due to their excessive length compared to linguistic modality. Abundant recent methods aim to solve this problem with token pruning, which first…

Camouflaged objects adaptively fit their color and texture with the environment, which makes them indistinguishable from the surroundings. Current methods revealed that high-level semantic features can highlight the differences between…

Accurate and robust detection of multi-class objects in optical remote sensing images is essential to many real-world applications such as urban planning, traffic control, searching and rescuing, etc. However, state-of-the-art object…

A large gap exists between fully-supervised object detection and weakly-supervised object detection. To narrow this gap, some methods consider knowledge transfer from additional fully-supervised dataset. But these methods do not fully…

Existing camouflage object detection (COD) methods typically rely on fully-supervised learning guided by mask annotations. However, obtaining mask annotations is time-consuming and labor-intensive. Compared to fully-supervised methods,…

Most existing image tokenizers encode images into a fixed number of tokens or patches, overlooking the inherent variability in image complexity. To address this, we introduce Content-Adaptive Tokenizer (CAT), which dynamically adjusts…

Collaborative Object Detection (COD) and collaborative perception can integrate data or features from various entities, and improve object detection accuracy compared with individual perception. However, adversarial attacks pose a potential…

While vision transformers have achieved impressive results, effectively and efficiently accelerating these models can further boost performances. In this work, we propose a dense/sparse training framework to obtain a unified model, enabling…

The core challenge in Camouflage Object Detection (COD) lies in the indistinguishable similarity between targets and backgrounds in terms of color, texture, and shape. This causes existing methods to either lose edge details (such as…

Deep convolutional neural networks are shown to be overkill with high parametric and computational redundancy in many application scenarios, and an increasing number of works have explored model pruning to obtain lightweight and efficient…

Vision Transformer (ViT)-based sparse multi-view 3D object detectors have achieved remarkable accuracy but still suffer from high inference latency due to heavy token processing. To accelerate these models, token compression has been widely…

Due to the high cost of collection and labeling, there are relatively few datasets for camouflaged object detection (COD). In particular, for certain specialized categories, the available image dataset is insufficiently populated. Synthetic…

Spotting camouflaged objects that are visually assimilated into the background is tricky for both object detection algorithms and humans who are usually confused or cheated by the perfectly intrinsic similarities between the foreground…

Modern two-stage object detectors generally require excessively large models for their detection heads to achieve high accuracy. To address this problem, we propose that the model parameters of two-stage detection heads can be condensed and…

In the world of deep learning, Transformer models have become very significant, leading to improvements in many areas from understanding language to recognizing images, covering a wide range of applications. Despite their success, the…

Semi-supervised Camouflaged Object Detection (SSCOD) aims to reduce reliance on costly pixel-level annotations by leveraging limited annotated data and abundant unlabeled data. However, existing SSCOD methods based on Teacher-Student…

Existing edge-aware camouflaged object detection (COD) methods normally output the edge prediction in the early stage. However, edges are important and fundamental factors in the following segmentation task. Due to the high visual…