paper-with-me

홈 › Papers

INSTA-BNN: Binary Neural Network with INSTAnce-aware Threshold

2022-04-15 · ICCV 2023 1 · Changhun Lee, HyungJun Kim, Eunhyeok Park, Jae-Joon Kim

Binary Neural Networks (BNNs) have emerged as a promising solution for reducing the memory footprint and compute costs of deep neural networks, but they suffer from quality degradation due to the lack of freedom as activations and weights are constrained to the binary values. To compensate for the accuracy drop, we propose a novel BNN design called Binary Neural Network with INSTAnce-aware threshold (INSTA-BNN), which controls the quantization threshold dynamically in an input-dependent or instance-aware manner. According to our observation, higher-order statistics can be a representative metric to estimate the characteristics of the input distribution. INSTA-BNN is designed to adjust the threshold dynamically considering various information, including higher-order statistics, but it is also optimized judiciously to realize minimal overhead on a real device. Our extensive study shows that INSTA-BNN outperforms the baseline by 3.0% and 2.8% on the ImageNet classification task with comparable computing cost, achieving 68.5% and 72.2% top-1 accuracy on ResNet-18 and MobileNetV1 based models, respectively.

📄 PDF Abstract BibTeX arXiv:2204.07439

Code (0)

등록된 구현이 없습니다.

Tasks

Quantization

Methods 이 논문이 사용한 방법론

Depthwise Convolution Depthwise Convolution is a type of convolution where we apply a single convolutional filter for each input channel. In the regular 2D…
Pointwise Convolution Pointwise Convolution is a type of convolution that uses a 1x1 kernel: a kernel that iterates through every single point. This…
Average Pooling 설명 없음
Depthwise Separable Convolution While standard convolution performs the channelwise and spatial-wise computation in one step, Depthwise Separable Convolution …
Batch Normalization 설명 없음
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
ReLU How Do I Communicate to Expedia? How Do I Communicate to Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Live Support & Special Travel…
Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…

Similar Papers 제목 키워드 기반

A multi-instance deep neural network classifier: application to Higgs boson CP measurement

2018-03-02 · P. Bialas, D. Nemeth, E. Richter-Wąs

We investigate properties of a classifier applied to the measurements of the CP state of the Higgs boson in $H\rightarrow\tau\tau$ decays. The problem is framed as binary classifier applied to individual instances. Then …

General Classification

SoftPQ: Robust Instance Segmentation Evaluation via Soft Matching and Tunable Thresholds

2025-05-17 · Ranit Karmakar, Simon F. Nørrelykke

Segmentation evaluation metrics traditionally rely on binary decision logic: predictions are either correct or incorrect, based on rigid IoU thresholds. Detection--based metrics such as F1 and mAP determine correctness a…

BenchmarkingBinary ClassificationInstance SegmentationSegmentation+1

Proximity-Based Evidence Retrieval for Uncertainty-Aware Neural Networks

2025-09-11 · Hassan Gharoun, Mohammad Sadegh Khorshidi, Kasra Ranjbarigderi, Fang Chen 외 arxiv

This work proposes an evidence-retrieval mechanism for uncertainty-aware decision-making that replaces a single global cutoff with an evidence-conditioned, instance-adaptive criterion. For each test instance, proximal ex…

InstanT: Semi-supervised Learning with Instance-dependent Thresholds

2023-10-29 · NeurIPS 2023 11

Semi-supervised learning (SSL) has been a fundamental challenge in machine learning for decades. The primary family of SSL algorithms, known as pseudo-labeling, involves assigning pseudo-labels to confident unlabeled ins…

Solution-aware vs global ReLU selection: partial MILP strikes back for DNN verification

2025-07-31 · Yuke Liao, Blaise Genest, Kuldeep Meel, Shaan Aryaman arxiv

To handle complex instances, we revisit a divide-and-conquer approach to break down the complexity: instead of few complex BaB calls, we rely on many small {\em partial} MILP calls. The crucial step is to select very few…