Spatially Optimized Compact Deep Metric Learning Model For Similarity Search

Abstract

Spatial optimization is often overlooked in many computer vision tasks. Filters should be able to recognize the features of an object regardless of where it is in the image. Similarity search is a crucial task where spatial features decide an important output. The capacity of convolution to capture visual patterns across various locations is limited. In contrast to convolution, the involution kernel is dynamically created at each pixel based on the pixel value and parameters that have been learned. This study demonstrates that utilizing a single layer of involution feature extractor alongside a compact convolution model significantly enhances the performance of similarity search. Additionally, we improve predictions by using the GELU activation function rather than the ReLU. The negligible amount of weight parameters in involution with a compact model with better performance makes the model very useful in real-world implementations. Our proposed model is below 1 megabyte in size. We ha

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyislam2024spatially

Related papers

• Deep Metric Learning Using Similarities From Nonlinear Rank Approximations (2019)2.26
• Local Similarity-aware Deep Feature Embedding (2016)0.00
• Visualizing Deep Similarity Networks (2019)11.85
• Fast Spectral Ranking For Similarity Search (2017)11.58
• Differential Geometric Retrieval Of Deep Features (2017)2.26
• Accurate Deep Representation Quantization With Gradient Snapping Layer For Similarity Search (2016)0.00
• Semantic Granularity Metric Learning For Visual Search (2019)7.81
• Learning Non-metric Visual Similarity For Image Retrieval (2017)11.58