Related papers: NIFF: Alleviating Forgetting in Generalized Few-Sh…

In recent years, knowledge distillation has been proved to be an effective solution for model compression. This approach can make lightweight student models acquire the knowledge extracted from cumbersome teacher models. However, previous…

In this paper, we present a simple and parameter-efficient drop-in module for one-stage object detectors like SSD when learning from scratch (i.e., without pre-trained models). We call our module GFR (Gated Feature Reuse), which exhibits…

Few-shot object detection (FSOD) aims to extract semantic knowledge from limited object instances of novel categories within a target domain. Recent advances in FSOD focus on fine-tuning the base model based on a few objects via…

Knowledge distillation (KD) has been widely applied in semantic segmentation to compress large models, but conventional approaches primarily preserve in-domain accuracy while neglecting out-of-domain generalization, which is essential under…

Data-Free Knowledge Distillation (DFKD) enables the knowledge transfer from the given pre-trained teacher network to the target student model without access to the real training data. Existing DFKD methods focus primarily on improving image…

Few-shot class-incremental learning is crucial for developing scalable and adaptive intelligent systems, as it enables models to acquire new classes with minimal annotated data while safeguarding the previously accumulated knowledge.…

In recent years, numerous domain adaptive strategies have been proposed to help deep learning models overcome the challenges posed by domain shift. However, even unsupervised domain adaptive strategies still require a large amount of target…

In this paper, we investigate the knowledge distillation (KD) strategy for object detection and propose an effective framework applicable to both homogeneous and heterogeneous student-teacher pairs. The conventional feature imitation…

The goal of few-shot image recognition (FSIR) is to identify novel categories with a small number of annotated samples by exploiting transferable knowledge from training data (base categories). Most current studies assume that the…

Data-Free Knowledge Distillation (DFKD) is a promising task to train high-performance small models to enhance actual deployment without relying on the original training data. Existing methods commonly avoid relying on private data by…

Camouflaged object detection and segmentation is a new and challenging research topic in computer vision. There is a serious issue of lacking data on concealed objects such as camouflaged animals in natural scenes. In this paper, we address…

Knowledge distillation is the process of transferring knowledge from a more powerful large model (teacher) to a simpler counterpart (student). Numerous current approaches involve the student imitating the knowledge of the teacher directly.…

Generalized few-shot semantic segmentation was introduced to move beyond only evaluating few-shot segmentation models on novel classes to include testing their ability to remember base classes. While the current state-of-the-art approach is…

Few-shot object detection (FSOD) aims to detect novel instances with only a limited number of labeled training samples, presenting a challenge that is particularly prominent in numerous remote sensing applications such as endangered species…

Few-shot segmentation aims to devise a generalizing model that segments query images from unseen classes during training with the guidance of a few support images whose class tally with the class of the query. There exist two…

Data-free knowledge distillation (DFKD) transfers knowledge from a teacher to a student without access to the real in-distribution (ID) data. While existing methods perform well on small-scale images, they suffer from mode collapse when…

In this paper, we propose a feature affinity (FA) assisted knowledge distillation (KD) method to improve quantization-aware training of deep neural networks (DNN). The FA loss on intermediate feature maps of DNNs plays the role of teaching…

Deep learning models have demonstrated remarkable success in object detection, yet their complexity and computational intensity pose a barrier to deploying them in real-world applications (e.g., self-driving perception). Knowledge…

While fine-tuning based methods for few-shot object detection have achieved remarkable progress, a crucial challenge that has not been addressed well is the potential class-specific overfitting on base classes and sample-specific…

Deep learning has achieved remarkable success in object recognition tasks through the availability of large scale datasets like ImageNet. However, deep learning systems suffer from catastrophic forgetting when learning incrementally without…