Related papers: Relational Self-supervised Distillation with Compa…
Monocular depth estimation (MDE) methods are often either too computationally expensive or not accurate enough due to the trade-off between model complexity and inference performance. In this paper, we propose a lightweight network that can…
Previous knowledge distillation (KD) methods mostly focus on compressing network architectures, which is not thorough enough in deployment as some costs like transmission bandwidth and imaging equipment are related to the image size.…
Distribution matching distillation (DMD) facilitates few-step image generation by aligning a distilled student with a reference multi-step teacher. In practice, however, optimizing DMD can reduce sample diversity in few-step synthesis, and…
Training deep neural networks has become increasingly demanding, requiring large datasets and significant computational resources, especially as model complexity advances. Data distillation methods, which aim to improve data efficiency,…
Knowledge distillation is an effective transfer of knowledge from a heavy network (teacher) to a small network (student) to boost students' performance. Self-knowledge distillation, the special case of knowledge distillation, has been…
Standard single-image super-resolution creates paired training data from high-resolution images through fixed downsampling kernels. However, real-world super-resolution (RWSR) faces unknown degradations in the low-resolution inputs, all the…
Self-supervised learning solves pretext prediction tasks that do not require annotations to learn feature representations. For vision tasks, pretext tasks such as predicting rotation, solving jigsaw are solely created from the input data.…
Despite achieving state-of-the-art performance, deep learning methods generally require a large amount of labeled data during training and may suffer from overfitting when the sample size is small. To ensure good generalizability of deep…
Regarding intelligent transportation systems, low-bitrate transmission via lossy point cloud compression is vital for facilitating real-time collaborative perception among connected agents, such as vehicles and infrastructures, under…
As the field continues its push for ever more resources, this work turns the spotlight on a critical question: how can vision-language models (VLMs) be adapted to thrive in low-resource, budget-constrained settings? While large VLMs offer…
Despite significant advancements of deep learning-based forgery detectors for distinguishing manipulated deepfake images, most detection approaches suffer from moderate to significant performance degradation with low-quality compressed…
Existing knowledge distillation methods mostly focus on distillation of teacher's prediction and intermediate activation. However, the structured representation, which arguably is one of the most critical ingredients of deep models, is…
Knowledge distillation has become a cornerstone technique in deep learning, facilitating the transfer of knowledge from complex models to lightweight counterparts. Traditional distillation approaches focus on transferring knowledge at the…
Self-supervised learning for time-series data holds potential similar to that recently unleashed in Natural Language Processing and Computer Vision. While most existing works in this area focus on contrastive learning, we propose a…
We propose a lightweight retrieval-based pipeline to predict 6DOF camera poses from RGB images. Our pipeline uses a convolutional neural network (CNN) to encode a query image as a feature vector. A nearest neighbor lookup finds the…
RGB-D salient object detection (SOD) demonstrates its superiority on detecting in complex environments due to the additional depth information introduced in the data. Inevitably, an independent stream is introduced to extract features from…
Large self-supervised models are effective feature extractors, but their application is challenging under on-device budget constraints and biased dataset collection, especially in keyword spotting. To address this, we proposed a knowledge…
Effectively structuring deep knowledge plays a pivotal role in transfer from teacher to student, especially in semantic vision tasks. In this paper, we present a simple knowledge structure to exploit and encode information inside the…
This paper studies the problem of pre-training for small models, which is essential for many mobile devices. Current state-of-the-art methods on this problem transfer the representational knowledge of a large network (as a Teacher) into a…
Masked image modeling (MIM) learns representations with remarkably good fine-tuning performances, overshadowing previous prevalent pre-training approaches such as image classification, instance contrastive learning, and image-text…