Recently, new paradigms of camouflaged object detection (COD), such as referring COD (Ref-COD) and collaborative COD (Co-COD), have been proposed to enhance task performance. However, there remains a lack of in-depth exploration of how to utilize reference information more effectively. In this paper, we introduce in-context learning camouflaged object detection (ICL-COD) as a novel paradigm of COD, which leverages camouflaged image samples and their corresponding annotations as visual examples to guide the model in better perceiving camouflage and recognizing camouflaged objects. We propose the ICL-Camo network, with the design of a context mining module (CMM) to mine fine-grained contextual information contained in the visual examples, and a context guiding module (CGM) that utilizes the contextual information mined from the examples as guidance to shift the attention of the target image features on potential camouflaged regions, thus enhancing its perception of camouflaged objects. Extensive experiments conducted on the COD benchmarks and other relevant tasks demonstrate the effectiveness of our proposed ICL-COD paradigm and ICL-Camo network. Code and results are available at: https://github.com/h0t-zer0/ICL-Camo.

Lightweight camouflaged object detection (COD) has garnered increasing attention due to its wide range of real-world applications and its efficiency on mobile devices. Existing lightweight COD methods typically attempt to utilize multi-scale fusion, frequency cues, and texture information to enhance the representation ability of lightweight backbone features. However, they still fall short in detecting precise and continuous object boundaries. To address this issue, we observe that two types of cells in the human visual system make great contributions to boundary perception. Motivated by this, we propose a boundary perception module (BPM) to enhance features with the awareness of fine-grained boundary, by mimicking the boundary perception process of aforementioned cells. In addition, we propose a bidirectional semantic enhancement module (BSEM) to effectively decode multi-level features in a lightweight manner. With BPM and BSEM, our proposed vision-inspired boundary perception network (BPNet) achieves superior performance against state-of-the-art methods and surpasses lightweight COD models by a large margin with the least parameters (3.64 M) and fastest speed (168FPS for the input size of 384 × 384).

Camouflaged Object Detection (COD) aims to segment objects resembling their environment. To address the challenges of extensive annotations and complex optimizations in supervised learning, recent prompt-based segmentation methods excavate insightful prompts from Large Vision-Language Models (LVLMs) and refine them using various foundation models. These are subsequently fed into the Segment Anything Model (SAM) for segmentation. However, due to the hallucinations of LVLMs and insufficient image-prompt interactions during the refinement stage, these prompts often struggle to capture well-established class differentiation and localization of camouflaged objects, resulting in performance degradation. To provide SAM with more informative prompts, we present UpGen, a pipeline that prompts SAM with generative prompts without requiring training, marking a novel integration of generative models with LVLMs. Specifically, we propose the Multi-Student-Single-Teacher (MSST) knowledge integration framework to alleviate hallucinations of LVLMs. This framework integrates insights from multiple sources to enhance the classification of camouflaged objects. To enhance interactions during the prompt refinement stage, we are the first to leverage generative models on real camouflage images to produce SAM-style prompts without fine-tuning. By capitalizing on the unique learning mechanism and structure of generative models, we effectively enable image-prompt interactions and generate highly informative prompts for SAM. Our extensive experiments demonstrate that UpGen outperforms weakly-supervised models and its SAM-based counterparts. We also integrate our framework into existing weakly-supervised methods to generate pseudo-labels, resulting in consistent performance gains. Moreover, with minor adjustments, UpGen shows promising results in open-vocabulary COD, referring COD, salient object detection, marine animal segmentation, and transparent object segmentation.

Existing camouflaged object detection (COD) methods typically have large model parameters and computations, hindering their deployment in real-world applications. Although using lightweight backbones can help alleviate this problem, their weaker feature representation often leads to performance degradation. To address this issue, we observe that frequency information has shown effective for cumbersome networks, but its effectiveness for lightweight ones has not been thoroughly investigated. Biological studies indicate that the human visual system utilizes distinct neural pathways to respond to different frequency stimuli, contributing to specialization and efficiency. Motivated by this, we propose an efficient frequency injection module (FIM) to aid lightweight backbone features by separately injecting detailed high frequency and object-level low frequency cues at each stage. FIM can be used as a plug-and-play component in existing COD networks to enhance backbone features at a low cost. With FIM, our proposed frequency injection network (FINet) achieves competitive performance against most state-ofthe- art methods with much faster speed (692FPS for the input size of 384 x 384) and fewer parameters (3.74M). Source codes will be released at https://github.com/crrcoo/FINet.

Current RGB-D salient object detection (RGB-D SOD) methods mainly develop a generalizable model trained by binary cross-entropy (BCE) loss based on convolutional or Transformer backbones. However, they usually exploit convolutional modules to fuse multi-modality features, with little attention paid to capturing the long-range multi-modality interactions for feature fusion. Furthermore, BCE loss does not explicitly explore intra- and inter-pixel relationships in a joint embedding space. To address these issues, we propose a cross-modality interaction parallel-transformer (CIPT) module, which better captures the long-range multi-modality interactions, generating more comprehensive fusion features. Besides, we propose a pixel-level contrastive learning (PCL) method that improves inter-pixel discrimination and intra-pixel compactness, resulting in a well-structured embedding space and a better saliency detector. Specifically, we propose an asymmetric network (TPCL) for RGB-D SOD, which consists of a Swin V2 Transformer-based backbone and a designed lightweight backbone (LDNet). Moreover, an edge-guided module and a feature enhancement (FE) module are proposed to refine the learned fusion features. Extensive experiments demonstrate that our method achieves excellent performance against 15 state-of-the-art methods on seven public datasets. We expect our work to facilitate the exploration of applying Transformer and contrastive learning for RGB-D SOD tasks.

Camouflaged object detection (COD) involves segmenting objects that share similar patterns, such as color and texture, with their surroundings. Current methods typically employ multiple well-designed modules or rely on edge cues to learn object feature representations for COD. However, these methods still struggle to capture the discriminative semantics between camouflaged objects (foreground) and background, possibly generating blurry prediction maps. To address these limitations, we propose a novel mask-and-edge co-guided separable network (MECS-Net) for COD that leverages both edge and mask cues to learn more discriminative representations and improve detection performance. Specifically, we design a mask-and-edge co-guided separable attention (MECSA) module, which consists of three flows for separately capturing edge, foreground, and background semantics. In addition, we propose a multi-scale enhancement fusion (MEF) module to aggregate multi-scale features of objects. The predictions are decoded in a top-down manner. Extensive experiments and visualizations demonstrate that our CNN-based and Transformer-based MECS-Net outperform 13 state-of-the-art methods on four popular COD datasets. Codes and results are availablehttps://github.com/TomorrowJW/MECS-Net-COD$\ast$.

The crowd statistics technology has been widely applied to smart classroom, manual roll call and campus security in recent years. However, due to challenges like low resolution, shooting angels and partial overlapping of students in the classroom, it's extremely hard to estimate the number of students accurately. Inspired by the improvements of object detection models in image target classification and location, we implements a classroom crowd statistics system (CCSS) to provide statistical information on the number of students for the construction of the wisdom classroom. In addition, we introduce a new large-scale classroom dataset, which contains 3,070 images in the classroom environment and 106,304 student annotations. To the best of our knowledge, this is the first student counting dataset collected under the classroom settings, which will greatly promote the development of classroom crowd statistics based on deep learning. In order to further improve the accuracy and speed of students detecting, we also modify the YOLOv4 algorithm to make it more adaptive for this task. The experimental results show that our model gains a significant improvement over the selected baselines on the proposed dataset.